Mapping the Intellectual Landscape Of Retrieval-Augmented Generation (RAG): A Bibliometric Analysis

The rapid growth of research on Retrieval-Augmented Generation shows a significant advancement towards the development of more reliable and interpretable artificial intelligence systems.However, the vast and fragmented nature of the existing studies makes it difficult for researchers to obtain a comprehensive and systematic overview of the field.To address this gap, this study presents the first bibliometric analysis of the Retrieval-Augmented Generation research landscape.By systematically mapping 3,948 peer-reviewed publications indexed in the Web of Science and Scopus databases (2020-2025), this study quantifies the field's rapid expansion, showing a 215.7% compound annual growth rate between 2020 and 2023, with more than 97% of all outputs published since early 2024.The analysis reveals a research ecosystem characterized by a bipolar geopolitical structure with China and the United States as the predominant contributors, supported by a collaborative "Triple Helix" network linking academia, industry, and government.Thematic analysis indicates a transition from linguistic foundations toward engineering-orientated challenges, with agent-based systems and knowledge graphs emerging as prominent areas of research.The main limitation of this study is the exclusion of preprint literature and unpublished research, which may omit emerging and significant studies.Overall, the findings offer a quantitative, data-driven roadmap to assist researchers, practitioners, and policymakers in artificial intelligence and related domains such as medicine and law in navigating this rapidly evolving field.